Intelligent caption systems and methods

Abstract

According to at least one embodiment, a system for generating a plurality of caption frames is provided. The system comprises a memory storing a plurality of elements generated from transcription information, at least one processor coupled to the memory, and a caption engine component executed by the at least one processor. The caption engine component is configured to identify at least one element sequence as meeting predetermined criteria specifying a plurality of caption characteristics, the at least one element sequence including at least one element of the plurality of elements, and store the at least one element sequence within at least one caption frame. The at least one element sequence may correspond to at least one sentence. The transcription information may be time-coded.

What is claimed is: 
     
       1. A system for generating a plurality of caption frames, the system comprising:
 a memory storing a plurality of elements generated from time-coded transcription information; 
 at least one processor coupled to the memory; and 
 a caption engine component executed by the at least one processor and configured to:
 identify at least one element sequence as meeting predetermined criteria specifying a plurality of caption characteristics of a caption to be stored within a caption frame of the plurality of caption frames, the at least one element sequence including at least one element of the plurality of elements, the predetermined criteria including a criterion specifying that the at least one element sequence have a minimum display duration greater than a predetermined duration; 
 store the at least one element sequence within the caption frame; 
 identify underutilized space within the caption frame; and 
 shift at least one of a begin time and an end time of another caption frame adjacent to the caption frame to encompass the underutilized space. 
 
 
     
     
       2. The system according to  claim 1 , wherein the caption engine component is further configured to:
 identify an element sequence as not meeting the predetermined criteria; 
 relax the predetermined criteria; 
 identify the element sequence as meeting the relaxed criteria; and 
 store the element sequence within the caption frame. 
 
     
     
       3. The system according to  claim 1 , wherein the at least one element sequence corresponds to at least one sentence. 
     
     
       4. The system according to  claim 1 , wherein the predetermined criteria includes a criterion specifying that text included in the at least one element sequence have a length less than a predetermined length. 
     
     
       5. The system according to  claim 4 , wherein the length reflects annotations included in the text. 
     
     
       6. The system according to  claim 1 , further comprising a plurality of element sequences including the at least one element sequence, each element sequence of the plurality of element sequences including elements of the plurality of elements, each element sequence of the plurality of element sequences meeting the predetermined criteria, and each element sequence of the plurality of element sequences being associated with a corresponding caption frame of the plurality of caption frames, wherein the caption engine component is further configured to associate elements included within the plurality of element sequences with caption frames included within the plurality of caption frames such that variance of a characteristic associated with the plurality of caption frames is reduced. 
     
     
       7. The system according to  claim 1 , further comprising a parser component executed by the at least one processor and configured to generate the plurality of elements by executing at least one parse of the time-coded transcription information. 
     
     
       8. The system according to  claim 7 , wherein the predetermined criteria includes a criterion specifying that elements including more complex grammatical structures be identified over elements including less complex grammatical structures. 
     
     
       9. The system according to  claim 7 , wherein the predetermined criteria includes a criterion specifying that the at least one element sequence end with an element other than an element deemed inseparable from a subsequent element. 
     
     
       10. The system according to  claim 9 , wherein the element deemed inseparable from the subsequent element includes at least one of a predetermined part-of-speech tag, a predetermined punctuation mark, and an annotation. 
     
     
       11. The system according to  claim 7 , wherein the parser component is configured to structure elements generated by the at least one parse into at least one parse tree. 
     
     
       12. The system according to  claim 7 , wherein the at least one parse includes a plurality of parses and each parse of the plurality of parses is associated with a score. 
     
     
       13. The system according to  claim 1 , wherein the minimum display duration is measured in at least one of duration per word and duration per character. 
     
     
       14. A method of generating a plurality of caption frames, the method comprising:
 identifying at least one element sequence as meeting predetermined criteria specifying a plurality of caption characteristics of a caption to be associated with a caption frame of the plurality of caption frames, the at least one element sequence including at least one element of a plurality of elements generated from time-coded transcription information, the predetermined criteria including a criterion specifying that the at least one element sequence have a minimum display duration greater than a predetermined duration; 
 associating the caption frame of the plurality of caption frames with the at least one element sequence; 
 identifying underutilized space within the caption frame; and 
 shifting at least one of a begin time and an end time of another caption frame adjacent to the caption frame to encompass the underutilized space. 
 
     
     
       15. The method according to  claim 14 , further comprising associating elements included within element sequences of a plurality of element sequences with caption frames included within the plurality of caption frames such that variance of a characteristic associated with the plurality of caption frames is reduced, each element sequence of the plurality of element sequences including elements of the plurality of elements, each element sequence of the plurality of element sequences meeting the predetermined criteria, and each element sequence of the plurality of element sequences being associated with a corresponding caption frame of the plurality of caption frames. 
     
     
       16. The method according to  claim 14 , further comprising executing at least one parse of transcription information to generate the plurality of elements. 
     
     
       17. The method according to  claim 16 , wherein identifying the at least one element sequence as meeting predetermined criteria includes identifying an element including more complex grammatical structures over an element including less complex grammatical structures. 
     
     
       18. A non-transitory computer readable medium storing instructions executable by at least one processor of a computer system, the instructions configuring the computer system to execute a process for generating a plurality of caption frames, the instructions including instructions that configure the computer system to:
 identify at least one element sequence as meeting predetermined criteria specifying a plurality of caption characteristics of a caption to be associated with a caption frame of the plurality of caption frames, the at least one element sequence including at least one element of a plurality of elements generated from time-coded transcription information, the predetermined criteria including a criterion specifying that the at least one element sequence have a minimum display duration greater than a predetermined duration; 
 associate the caption frame of the plurality of caption frames with the at least one element sequence; 
 identify underutilized space within the caption frame; and 
 shift at least one of a begin time and an end time of another caption frame adjacent to the caption frame to encompass the underutilized space. 
 
     
     
       19. The computer readable medium according to  claim 18 , wherein the instructions further configure the computer system to execute at least one parse of transcription information to generate the plurality of elements and wherein the instructions to identify the at least one element sequence as meeting predetermined criteria include instructions to identify an element including more complex grammatical structures over an element including less complex grammatical structures.